{"total":308,"rows":[{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585,"area":"diffusion"},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355,"area":"diffusion"},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614,"area":"diffusion"},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245,"area":null},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106,"area":"diffusion"},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774,"area":"diffusion"},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727,"area":null},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703,"area":"diffusion"},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702,"area":"diffusion"},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694,"area":null},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648,"area":null},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615,"area":"mllm"},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502,"area":"diffusion"},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492,"area":null},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487,"area":null},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388,"area":"diffusion"},{"id":"2303.13516","title":"Ablating Concepts in Text-to-Image Diffusion Models","created":"2023-03-23","cited_by_count":317,"area":"diffusion"},{"id":"2204.14217","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","created":"2022-04-28","cited_by_count":307,"area":null},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260,"area":null},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259,"area":null},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253,"area":null},{"id":"2306.07954","title":"Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation","created":"2023-06-13","cited_by_count":253,"area":"diffusion"},{"id":"2202.04053","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","created":"2022-02-08","cited_by_count":230,"area":"lr"},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212,"area":"diffusion"},{"id":"2302.04222","title":"Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models","created":"2023-02-08","cited_by_count":205,"area":"diffusion"},{"id":"2302.12228","title":"Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models","created":"2023-02-23","cited_by_count":203,"area":"diffusion"},{"id":"2212.04489","title":"SINE: SINgle Image Editing with Text-to-Image Diffusion Models","created":"2022-12-08","cited_by_count":159,"area":"diffusion"},{"id":"2312.03209","title":"Cache Me if You Can: Accelerating Diffusion Models through Block Caching","created":"2023-12-06","cited_by_count":151,"area":"diffusion"},{"id":"2201.07520","title":"CM3: A Causal Masked Multimodal Model of the Internet","created":"2022-01-19","cited_by_count":142,"area":null},{"id":"2305.18295","title":"RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths","created":"2023-05-29","cited_by_count":142,"area":"diffusion"},{"id":"2312.10240","title":"Rich Human Feedback for Text-to-Image Generation","created":"2023-12-15","cited_by_count":141,"area":"diffusion"},{"id":"2305.18264","title":"Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising","created":"2023-05-29","cited_by_count":139,"area":"diffusion"},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137,"area":null},{"id":"2111.13792","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","created":"2021-11-27","cited_by_count":128,"area":null},{"id":"2404.04650","title":"InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization","created":"2024-04-06","cited_by_count":123,"area":"diffusion"},{"id":"2210.15257","title":"ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts","created":"2022-10-27","cited_by_count":112,"area":"diffusion"},{"id":"2103.10951","title":"Paint by Word","created":"2021-03-19","cited_by_count":107,"area":null},{"id":"2310.10123","title":"AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion","created":"2023-10-16","cited_by_count":100,"area":"diffusion"},{"id":"2305.04441","title":"Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models","created":"2023-05-08","cited_by_count":99,"area":"diffusion"},{"id":"2304.05390","title":"HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models","created":"2023-04-11","cited_by_count":95,"area":"diffusion"},{"id":"2306.05414","title":"Improving Tuning-Free Real Image Editing with Proximal Guidance","created":"2023-06-08","cited_by_count":87,"area":"diffusion"},{"id":"2301.12959","title":"GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis","created":"2023-01-30","cited_by_count":85,"area":"diffusion"},{"id":"2306.14544","title":"A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis","created":"2023-06-26","cited_by_count":78,"area":"diffusion"},{"id":"2311.17002","title":"Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following","created":"2023-11-28","cited_by_count":77,"area":"diffusion"},{"id":"2211.13319","title":"Make-A-Story: Visual Memory Conditioned Consistent Story Generation","created":"2022-11-23","cited_by_count":76,"area":null},{"id":"2112.05130","title":"Multimodal Conditional Image Synthesis with Product-of-Experts GANs","created":"2021-12-09","cited_by_count":75,"area":null},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75,"area":"diffusion"},{"id":"2305.16225","title":"ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models","created":"2023-05-25","cited_by_count":75,"area":"diffusion"},{"id":"2310.13828","title":"Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":75,"area":"safety"},{"id":"2209.06192","title":"StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation","created":"2022-09-13","cited_by_count":74,"area":null},{"id":"2112.01573","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","created":"2021-12-02","cited_by_count":71,"area":null},{"id":"2404.08031","title":"Latent Guard: a Safety Framework for Text-to-image Generation","created":"2024-04-11","cited_by_count":71,"area":null},{"id":"2304.01816","title":"Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation","created":"2023-04-04","cited_by_count":68,"area":null},{"id":"2211.00924","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","created":"2022-11-02","cited_by_count":65,"area":null},{"id":"2104.00924","title":"Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning","created":"2021-04-02","cited_by_count":62,"area":null},{"id":"2107.02423","title":"Improving Text-to-Image Synthesis Using Contrastive Learning","created":"2021-07-06","cited_by_count":62,"area":null},{"id":"2207.09446","title":"ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model","created":"2022-07-19","cited_by_count":62,"area":null},{"id":"2304.02051","title":"Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing","created":"2023-04-04","cited_by_count":62,"area":"diffusion"},{"id":"2305.16223","title":"Prompt-Free Diffusion: Taking \"Text\" out of Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":62,"area":"diffusion"},{"id":"2203.00386","title":"CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP","created":"2022-03-01","cited_by_count":60,"area":null},{"id":"2303.09319","title":"Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generation","created":"2023-03-16","cited_by_count":60,"area":"diffusion"},{"id":"2307.09036","title":"PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation","created":"2023-07-18","cited_by_count":58,"area":null},{"id":"2411.19417","title":"Any-Resolution AI-Generated Image Detection by Spectral Learning","created":"2024-11-28","cited_by_count":57,"area":null},{"id":"2312.06059","title":"CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image Diffusion Models","created":"2023-12-11","cited_by_count":54,"area":"diffusion"},{"id":"2104.00567","title":"Text to Image Generation with Semantic-Spatial Aware GAN","created":"2021-04-01","cited_by_count":53,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2308.12038","title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages","created":"2023-08-23","cited_by_count":52,"area":"mllm"},{"id":"2309.00810","title":"RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model","created":"2023-09-02","cited_by_count":47,"area":"diffusion"},{"id":"2108.12141","title":"DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis","created":"2021-08-27","cited_by_count":45,"area":null},{"id":"2206.07771","title":"Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation","created":"2022-06-15","cited_by_count":44,"area":"diffusion"},{"id":"2305.11080","title":"Inspecting the Geographical Representativeness of Images from Text-to-Image Models","created":"2023-05-18","cited_by_count":44,"area":"diffusion"},{"id":"2502.06130","title":"Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models","created":"2025-02-10","cited_by_count":44,"area":"mllm"},{"id":"2105.10026","title":"Improving Generation and Evaluation of Visual Stories via Semantic Consistency","created":"2021-05-20","cited_by_count":43,"area":null},{"id":"2305.13579","title":"Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach","created":"2023-05-23","cited_by_count":43,"area":null},{"id":"2403.01693","title":"HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances","created":"2024-03-04","cited_by_count":42,"area":"diffusion"},{"id":"2110.09753","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","created":"2021-10-19","cited_by_count":41,"area":null},{"id":"2112.15283","title":"ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation","created":"2021-12-31","cited_by_count":41,"area":null},{"id":"2206.13508","title":"Data Augmentation techniques in time series domain: A survey and taxonomy","created":"2022-06-25","cited_by_count":41,"area":null},{"id":"2305.01795","title":"Multimodal Procedural Planning via Dual Text-Image Prompting","created":"2023-05-02","cited_by_count":40,"area":null},{"id":"2312.12416","title":"Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models","created":"2023-12-19","cited_by_count":40,"area":"diffusion"},{"id":"2211.14842","title":"Unified Discrete Diffusion for Simultaneous Vision-Language Generation","created":"2022-11-27","cited_by_count":39,"area":"diffusion"},{"id":"2206.09479","title":"StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis","created":"2022-06-19","cited_by_count":38,"area":null},{"id":"2402.02333","title":"Copyright Protection in Generative AI: A Technical Perspective","created":"2024-02-04","cited_by_count":38,"area":null},{"id":"2401.04608","title":"EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models","created":"2024-01-09","cited_by_count":37,"area":"diffusion"},{"id":"2105.14211","title":"M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers","created":"2021-05-29","cited_by_count":36,"area":null},{"id":"2205.13445","title":"Mutual Information Divergence: A Unified Metric for Multimodal Generative Models","created":"2022-05-25","cited_by_count":35,"area":null},{"id":"2308.13812","title":"Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs","created":"2023-08-26","cited_by_count":35,"area":"diffusion"},{"id":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34,"area":"diffusion"},{"id":"2203.15334","title":"AnyFace: Free-style Text-to-Face Synthesis and Manipulation","created":"2022-03-29","cited_by_count":33,"area":null},{"id":"2203.15799","title":"StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis","created":"2022-03-29","cited_by_count":33,"area":null},{"id":"2307.04749","title":"Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback","created":"2023-07-10","cited_by_count":32,"area":"diffusion"},{"id":"2401.02015","title":"Improving Diffusion-Based Image Synthesis with Context Prediction","created":"2024-01-04","cited_by_count":32,"area":"diffusion"},{"id":"2210.16031","title":"UPainting: Unified Text-to-Image Diffusion Generation with Cross-modal Guidance","created":"2022-10-28","cited_by_count":30,"area":"diffusion"},{"id":"2303.12343","title":"LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation","created":"2023-03-22","cited_by_count":29,"area":"diffusion"},{"id":"2305.13607","title":"Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation","created":"2023-05-23","cited_by_count":28,"area":null},{"id":"2311.17060","title":"Material Palette: Extraction of Materials from a Single Image","created":"2023-11-28","cited_by_count":28,"area":null}],"next_cursor":"100"}